Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    emis
    -0.68
    */(
    -0.67
     [+
    -0.66
    ulet
    -0.66
    chell
    -0.65
     bluff
    -0.65
    anu
    -0.64
    psey
    -0.64
    ramer
    -0.64
    ouver
    -0.63
    POSITIVE LOGITS
     Styles
    0.74
    ADA
    0.72
     Eaton
    0.67
    DIV
    0.66
     Generations
    0.66
    IDS
    0.66
    ECA
    0.66
    SEE
    0.66
     rgb
    0.66
    Altern
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.